Bolt Looseness Damage Detection using Lamb Wave Gaussian Mixture Model
-
摘要: 螺栓连接广泛应用于多种领域,及时发现螺栓松动的位置是结构健康监测的重要课题之一。利用粘贴在铝板上的压电阵列采集Lamb波信号,提取特征参数集建立高斯混合模型。通过采集监测区域内螺栓连接结构的各种松动工况的数据建立完备的基准数据库,更新实时数据建立动态高斯混合模型,基于高斯混合模型之间概率密度分布之间的相似度最大准则,判断监测区域的各个螺栓松动情况。实验结果表明,螺栓松紧状态一致的测试样本与训练样本之间的高斯混合模型概率分布相似度值达到0.99以上,明显高于工况不匹配的相似度,该方法可有效判断监测区域每个螺栓的松紧状态。Abstract: Bolted-joints are widely used in many fields. The discovery of the position of bolt looseness in time is one of the most important topics of structural health monitoring. The Gaussian mixture model is established by using the feature parameter sets, which are extracted from the Lamb wave signal collected by the piezoelectric array attached to an aluminum plate. The complete reference database is established by collecting the data of various looseness working conditions in the bolted-joint structure of the monitoring area. The real-time data is updated to establish the dynamic Gaussian mixture model, and the looseness of each bolt in the monitoring area is judged based on the maximum similarity criterion between the probability density distributions of the Gaussian mixture model. The experimental results show that the probability distribution similarity of the Gaussian mixture model between the test sample and the training sample in a consistent bolt tightness state is above 0.99, which is obviously higher than the probability distribution similarity in the inconsistent working condition. This method can effectively judge the state of each bolt in the monitoring area.
-
表 1 不同工况对应的螺栓松紧状态
螺栓 工况1 工况2 工况3 工况4 A 拧紧 松动 松动 拧紧 B 拧紧 拧紧 松动 松动 -
[1] 杜飞, 徐超.螺栓连接松动的导波监测技术综述[J].宇航总体技术, 2018, 2(4):13-23 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181202011526Du F, Xu C. A review on bolt preload monitoring using guided waves[J]. Astronautical Systems Engineering Technology, 2018, 2(4):13-23(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181202011526 [2] 茅正冲, 涂文辉.基于分层识别的快速说话人识别研究[J].计算机工程与技术, 2018, 40(7):1244-1249 http://d.old.wanfangdata.com.cn/Periodical/jsjgcykx201807015Mao Z C, Tu W H. Fast speaker recognition based on hierarchical recognition[J]. Computer Engineering and Science, 2018, 40(7):1244-1249(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjgcykx201807015 [3] 朱文杰, 王广龙, 田杰, 等.空时自适应混合高斯模型复杂背景运动目标检测[J].北京理工大学学报, 2018, 38(2):165-172 http://d.old.wanfangdata.com.cn/Periodical/bjlgdxxb201802010Zhu W J, Wang G L, Tian J, et al. Spatio-temporal adaptive mixture of Gaussians for moving objects detection in complex background scenes[J]. Transactions of Beijing Institute of Technology, 2018, 38(2):165-172(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/bjlgdxxb201802010 [4] 柴五一, 杨丰, 袁绍锋, 等.用于图像分割的多分类高斯混合模型和基于邻域信息的高斯混合模型[J].计算机科学, 2018, 45(11):272-277 http://d.old.wanfangdata.com.cn/Periodical/jsjkx201811044Chai W Y, Yang F, Yuan S F, et al. Multi-class Gaussian mixture model and neighborhood information based Gaussian mixture model for image segmentation[J]. Computer Science, 2018, 45(11):272-277(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjkx201811044 [5] Qiu L, Yuan S F, Bao Q, et al. Crack propagation monitoring in a full-scale aircraft fatigue test based on guided wave-Gaussian mixture model[J]. Smart Materials and Structures, 2016, 25(5):055048 doi: 10.1088/0964-1726/25/5/055048 [6] 邱雷, 房芳, 袁慎芳, 等.导波强化裂变聚合概率模型损伤监测方法[J].振动、测试与诊断, 2018, 38(3):438-445 http://d.old.wanfangdata.com.cn/Periodical/zdcsyzd201803002Qiu L, Fang F, Yuan S F, et al. Guided wave and enhanced split merge probability model based on damage evaluation method[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(3):438-445(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdcsyzd201803002 [7] Banerjee S, Qing X P, Beard S, et al. Prediction of progressive damage state at the hot spots using statistical estimation[J]. Journal of Intelligent Material Systems and Structures 2010, 21(6):595-605 doi: 10.1177/1045389X10361632 [8] Chakraborty D, Kovvali N, Papandreou-Suppappola A, et al. An adaptive learning damage estimation method for structural health monitoring[J]. Journal of Intelligent Material Systems and Structures, 2015, 26(2):125-143 doi: 10.1177/1045389X14522531 [9] Tsch pe C, Wolff M. Statistical classifiers for structural health monitoring[J]. IEEE Sensors Journal, 2009, 9(11):1567-1576 doi: 10.1109/JSEN.2009.2019330 [10] Wang Q, Ma S X, Yue D. Identification of damage in composite structures using Gaussian Mixture Model-processed Lamb waves[J]. Smart Materials and Structures, 2018, 27(4):045007 doi: 10.1088/1361-665X/aaaf96 [11] 张雪峰, 马静, 关崴, 等.基于高斯混合模型的滚动轴承故障诊断[J].时代汽车, 2018(12):188-190 http://d.old.wanfangdata.com.cn/Periodical/sdqc201812080Zhang X F, Ma J, Guan W, et al. Rolling bearing fault diagnosis based on gaussian mixture model[J]. Auto Time, 2018(12):188-190(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/sdqc201812080 [12] 龙铭, 文章, 黄文艺, 等.滚动轴承故障程度评估的AR-GMM方法[J].机械科学与技术, 2016, 35(8):1183-1188 doi: 10.13433/j.cnki.1003-8728.2016.0806Long M, Wen Z, Huang W Y, et al. Assessment of rolling bearing fault degree using AR-GMM[J]. Mechanical Science and Technology for Aerospace Engineering, 2016, 35(8):1183-1188(in Chinese) doi: 10.13433/j.cnki.1003-8728.2016.0806 [13] 肖涵.基于高斯混合模型与子空间技术的故障识别研究[D].武汉: 武汉科技大学, 2007Xiao H. The research on fault identification based on Gaussian mixture model and subspace methods[D]. Wuhan: Wuhan University of Science and Technology, 2007(in Chinese) [14] 袁慎芳.结构健康监控[M].北京:国防工业出版社, 2007Yuan S F. Structural health monitoring and damage control[M]. Beijing:National Defense Industry Press, 2007(in Chinese) [15] Banfield J D, Raftery A E. Model-based Gaussian and non-Gaussian clustering[J]. Biometrics, 1993, 49(3):803-821 doi: 10.2307/2532201